Mobile-based peer-to-peer learning prototype for smallholder dairy producers

Abstract

About half of Africa's animal production comes from smallholder dairy farmers, who employ various strategies to maximize milk output. Some time-consuming and expensive heuristics are used by smallholder dairy farmers to increase milk yield, trapping them in a cycle of failure and lowering their incentive to continue making agricultural investments. Grouping smallholder dairy producers with comparable characteristics makes information sharing and interventions easier, increasing milk output. This study aimed at developing a mobile-based peer-to-peer learning prototype which considers farmers’ homogeneity with respect to husbandry practices and auto-allocates them to their respective production clusters. The developed prototype's rule-based engine handles the auto-allocation procedure by grouping farmers with similar farming characteristics into the proper production clusters. Smallholder dairy producers exchange knowledge and expertise through these groups to increase milk output. In Tanzania's Arusha Region, 69 smallholder dairy farmers and nine extension workers responded to a questionnaire to provide information, which was then analyzed using R programming. The important findings are; smallholder dairy producers were automatically allocated to their clusters based on their milk output. Cluster position regarding milk yields was determined using cluster performance for overall production attributes. Consequently, high yielding smallholder dairy producers are assigned to the high-yielding cluster, and vice versa, and extension officers provide timely support. This study is unique since smallholder dairy producers may use it to share dairy farming expertise and boost milk output. Mobile-based peer-to-peer should be integrated with the market by engaging enterprises that process milk for other milk products